Global-Local Multiple Granularity Learning for Cross-Modality Visible-Infrared Person Reidentification

Zhang, Liyan; Du, Guodong; Liu, Fan; Tu, Huawei; Shu, Xiangbo

doi:10.1109/tnnls.2021.3085978

Cited by 44 publications

(27 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regarding feature alignment, there are a lot of approaches [ 5 , 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 , 42 , 43 , 44 , 45 , 46 , 47 ]. The most popular architecture [ 5 , 35 , 48 ] is a double-stream deep network, where shallow layers are independent for learning modal-specific features and deep layers are shared for learning modal-common features.…”

Section: Related Workmentioning

confidence: 99%

Margin-Based Modal Adaptive Learning for Visible-Infrared Person Re-Identification

Zhao

Zhu

2023

Sensors

View full text Add to dashboard Cite

Visible-infrared person re-identification (VIPR) has great potential for intelligent transportation systems for constructing smart cities, but it is challenging to utilize due to the huge modal discrepancy between visible and infrared images. Although visible and infrared data can appear to be two domains, VIPR is not identical to domain adaptation as it can massively eliminate modal discrepancies. Because VIPR has complete identity information on both visible and infrared modalities, once the domain adaption is overemphasized, the discriminative appearance information on the visible and infrared domains would drain. For that, we propose a novel margin-based modal adaptive learning (MMAL) method for VIPR in this paper. On each domain, we apply triplet and label smoothing cross-entropy functions to learn appearance-discriminative features. Between the two domains, we design a simple yet effective marginal maximum mean discrepancy (M3D) loss function to avoid an excessive suppression of modal discrepancies to protect the features’ discriminative ability on each domain. As a result, our MMAL method could learn modal-invariant yet appearance-discriminative features for improving VIPR. The experimental results show that our MMAL method acquires state-of-the-art VIPR performance, e.g., on the RegDB dataset in the visible-to-infrared retrieval mode, the rank-1 accuracy is 93.24% and the mean average precision is 83.77%.

show abstract

Section: Related Workmentioning

confidence: 99%

Margin-Based Modal Adaptive Learning for Visible-Infrared Person Re-Identification

Zhao

Zhu

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…To select useful features, Wei et al [31] designed a flexible body partition module to distinguish part representations automatically. Zhang et al concatenated the global feature and local feature to create a more powerful feature descriptor [32]. In [33], aiming to eliminate the interference of background information, the authors exploited the knowledge of human body parts to extract robust features.…”

Section: Milestones Of Existing Vi-reid Studiesmentioning

confidence: 99%

Visible-Infrared Person Re-Identification: A Comprehensive Survey and a New Setting

et al. 2022

View full text Add to dashboard Cite

Person re-identification (ReID) plays a crucial role in video surveillance with the aim to search a specific person across disjoint cameras, and it has progressed notably in recent years. However, visible cameras may not be able to record enough information about the pedestrian’s appearance under the condition of low illumination. On the contrary, thermal infrared images can significantly mitigate this issue. To this end, combining visible images with infrared images is a natural trend, and are considerably heterogeneous modalities. Some attempts have recently been contributed to visible-infrared person re-identification (VI-ReID). This paper provides a complete overview of current VI-ReID approaches that employ deep learning algorithms. To align with the practical application scenarios, we first propose a new testing setting and systematically evaluate state-of-the-art methods based on our new setting. Then, we compare ReID with VI-ReID in three aspects, including data composition, challenges, and performance. According to the summary of previous work, we classify the existing methods into two categories. Additionally, we elaborate on frequently used datasets and metrics for performance evaluation. We give insights on the historical development and conclude the limitations of off-the-shelf methods. We finally discuss the future directions of VI-ReID that the community should further address.

show abstract

“…We can see that our AGMNet sets a new state of the art on SYSU-MM01, achieving 69.63% Rank-1 accuracy, 66.11% mAP and 52.24% mINP under all-search mode and 74.68% Rank-1 accuracy, 78.30% mAP and 74.00% mINP under indoor-search mode. Although some methods (FBP-AL [33], GLMC [45] and HTL [17]) introduce part-based convolutional features to improve retrieval performance, AGMNet still shows meaningful performance gain in terms of Rank-1/mAP/mINP (69.63% vs 64.37%, 66.11% vs 63.43% and 52.24% vs 39.54%).…”

Section: E Comparison To the State-of-the-artmentioning

confidence: 99%

Towards Homogeneous Modality Learning and Multi-Granularity Information Exploration for Visible-Infrared Person Re-Identification

Liu¹,

Xia²,

Jiang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Global-Local Multiple Granularity Learning for Cross-Modality Visible-Infrared Person Reidentification

Cited by 44 publications

References 0 publications

Margin-Based Modal Adaptive Learning for Visible-Infrared Person Re-Identification

Margin-Based Modal Adaptive Learning for Visible-Infrared Person Re-Identification

Visible-Infrared Person Re-Identification: A Comprehensive Survey and a New Setting

Towards Homogeneous Modality Learning and Multi-Granularity Information Exploration for Visible-Infrared Person Re-Identification

Contact Info

Product

Resources

About